(29 days)
cvi42 is intended to be used for viewing, post-processing, qualitative and quantitative evaluation of cardiovascular magnetic resonance (MR) images and computed tomography (CT) images in a Digital Imaging and Communications in Medicine (DICOM) Standard format.
lt enables:
· Importing cardiac MR & CT Images in DICOM format.
• Supporting clinical diagnostics by qualitative analysis of cardiac MR & CT images using display functionality such as panning, windowing, zooming, navigation through series/slices and phases, 3D reconstruction of images including multiplanar reconstructions of the images.
• Supporting clinical diagnostics by quantitative measurement of the heart and adjacent vessels in cardiac MR & CT images, specifically signal intensity, distance, area, volume, and mass.
• Supporting clinical diagnostics by using area and volume for measuring cardiac function and derived parameters cardiac output and cardiac index in long axis and short axis cardiac MR & CT images.
• Flow quantifications based on velocity encoded cardiac MR images (including two and four dimensional flow analysis).
• Strain analysis of cardiac MR images by providing measurements of 2D LV myocardial function (displacement, velocity, strain, strain rate, time to peak, and torsion).
· Supporting clinical diagnostics of cardiac CT images including quantitative measurements of calcified plaques in the coronary arteries (calcium scoring), specifically Agatston and volume and mass calcium scores, visualization and quantitative measurement of heart structures including coronaries, femoral, aortic, and mitral valves.
· Evaluating CT and MR images of blood vessels. Combining digital image processing and visualization tools such as multiplanar reconstruction (MPR), thin/thick maximum intensity projection (MIP), inverted MIP thin/thick, volume rendering technique (VRT), curved planar reformation (CPR), processing tools such as bone removal (based on both single energy and dual energy) table removal and evaluation tools (vessel centerline calculation, lumen calculation, stenosis calculation) and reporting tools (lesion location, lesion characteristics) and key images. The software package is designed to support the physician in confirming the presence of physician identified lesion in blood vessels and evaluation, documentation and follow up of any such lesions.
cvi42 shall be used by qualified medical professionals, experienced in examining and evaluating cardiovascular MR or CT images, for the purpose of obtaining diagnostic information as part of a comprehensive diagnostic decision-making process. cvi42 is a software application that can be used as a stand-alone product or in a networked environment.
The target population for cvi42 and its manual workflows is not restricted; however, cvi42's semiautomated machine learning algorithms, included in the MR Function and CORE CT modules, are intended for an adult population. Further, image acquisition by a cardiac MR or CT scanner may limit the use of the software for certain sectors of the general public.
cvi42 shall not be used to view or analyze images of any part of the body except the cardiac images acquired from a cardiovascular magnetic resonance or computed tomography scanner.
cvi42 Software Application ("cvi42") is a software as a medical device (SaMD) that is intended for evaluating CT and MR images of the cardiovascular system. Combining digital image processing, visualization, quantification, and reporting tools, cvi42 is designed to support physicians in the evaluation and analysis of cardiovascular imaqing studies.
cvi42 uses machine learning techniques to aid in semi-automatic contouring of regions of interest in cardiac MR or CT images.
The data used to train these machine learning algorithms were sourced from multiple clinical sites from urban centers and from different countries. When selecting data for training, the importance of model generalization was considered and data was selected such that a good distribution of patient demographics, scanner, and image parameters were represented. The separation into training versus validation datasets is made on the study level to ensure no overlap between the two sets. As such, different scans from the same study were not split between the training and validation datasets. None of the cases used for model validation were used for training the machine learning models.
cvi42 has a graphical user interface which allows users to analyze cardiac MR & CT images qualitatively and quantitatively.
cvi42 accepts uploaded data files previously acquired by MR or CT scanners or other data collection equipment but does not interface directly with such equipment. Its functionality is independent of the type of vender acquisition equipment. The analysis results are available onscreen and can be saved with the software for future review.
Here's a breakdown of the acceptance criteria and study details for the cvi42 Software Application, based on the provided document:
1. Table of Acceptance Criteria and Reported Device Performance
For cvi42 Auto (MR-CMR Function, CORE CT Coronary, and CORE CT-Calcium):
| Module | Acceptance Criteria | Reported Device Performance |
|---|---|---|
| CMR Function Analysis | Classification Accuracy: Based on True Positives (TP), True Negatives (TN), False Positives (FP), and False Negatives (FN).Mean Volume Prediction Error (MAE): For Short Axis (SAX) and Long Axis (LAX) volumetric measurements. | Series Classification Performance: 97% - 100%Volumetric MAE (SAX): 7% - 10%Volumetric MAE (LAX): 5% - 9% |
| Calcium Analysis | Classification Accuracy: Based on TP, TN, FP, and FN. | Classification Performance: 86% - 99% |
| Coronary Analysis | Centerline Quality and Performance: Based on TP and FN.Success Rate for Relevant Masks. | Centerline Performance: 82% - 94%Mask Performance: 98% - 100% |
For CORE CT (CT Function Module):
| Metric | Acceptance Criteria | Reported Device Performance (compared to a reference standard established from three expert readers) |
|---|---|---|
| LV Cavity Segmentation | Not explicitly stated numerical acceptance criteria, but implied to be within acceptable clinical limits for MAE, Dice, HD, and EF bias compared to expert readers. | MAE: Less than 10% difference.Dice Coefficient: Above 86%.3D Hausdorff Distance (HD): Below 9.5 mm.EF Bias: 1.3% with a 95% confidence interval of [-12, 14]. |
| RV Cavity Segmentation | Not explicitly stated numerical acceptance criteria, but implied to be within acceptable clinical limits for MAE, Dice, HD, and EF bias compared to expert readers. | MAE: Less than 18%.Dice Coefficient: Above 85%.HD: Below 18 mm.EF Bias: -5.5% with a 95% confidence interval of [-15, 4.4]. |
| LV Myocardium Segmentation | Not explicitly stated numerical acceptance criteria, but implied to be within acceptable clinical limits for MAE, Dice, and HD compared to expert readers. | MAE: Less than 17%.Dice Coefficient: Above 82%.HD: Below 15 mm. |
2. Sample Size for the Test Set and Data Provenance
For cvi42 Auto (MR-CMR Function, CORE CT Coronary, and CORE CT-Calcium):
- Sample Size: n = 235 anonymized patient images acquired from major vendors of MR and CT imaging devices.
- 70 samples for Coronary Analysis
- 102 samples for Calcium analysis
- 63 samples for SAX Function contouring
- 63 samples for each of 2-CV, 3-CV, and 4CV LAX function contouring
- 252 samples for Function Classification
- Data Provenance: Images were acquired from major vendors of MR and CT imaging devices. At least 50% of the data came from a U.S. population. The document does not specify if the data was retrospective or prospective, but the phrasing "were used for the validation" implies retrospective use of existing data.
For CORE CT (CT Function Module):
- Sample Size: Not explicitly stated, but the validation data was sourced from 9 different sites.
- Data Provenance: Sourced from 9 different sites, with 90% of the data sampled from US sources. The document does not specify if the data was retrospective or prospective.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications
For CORE CT (CT Function Module):
- Number of Experts: Three expert readers.
- Qualifications: "Expert readers" – specific qualifications (e.g., years of experience, board certification) are not detailed in the provided text.
For cvi42 Auto (MR-CMR Function, CORE CT Coronary, and CORE CT-Calcium), the document does not explicitly state the number of experts used to establish ground truth for the test set. It does mention expert readers for the comparison in the CORE CT section.
4. Adjudication Method for the Test Set
For CORE CT (CT Function Module):
- The "reference standard" was "established from three expert readers." The specific adjudication method (e.g., majority vote, specific consensus process) is not detailed, but it implies a consensus or agreement among these three experts.
For cvi42 Auto (MR-CMR Function, CORE CT Coronary, and CORE CT-Calcium):
- The document does not explicitly state the adjudication method for establishing ground truth for these modules.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done
- No, an MRMC comparative effectiveness study was not explicitly stated to have been done to measure human reader improvement with AI vs. without AI assistance. The performance tests described are primarily focused on the standalone performance of the AI algorithms (Machine Learning Derived Outputs) compared to a ground truth or a reference standard established by experts.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was done
- Yes, standalone performance was assessed. The sections titled "Validation of Machine Learning Derived Outputs" and "CORE CT: CT Function" describe the evaluation of the algorithms' performance (e.g., classification accuracy, MAE, Dice coefficient, HD, EF bias) against pre-defined acceptance criteria and a reference standard made by experts, without human-in-the-loop assistance for the AI's output generation. This is a standalone assessment of the algorithms.
7. The Type of Ground Truth Used
- Expert Consensus: For the CORE CT module, the ground truth (reference standard) used for evaluation was established by "three expert readers." This implies an expert consensus or expert-derived ground truth.
- For other modules (cvi42 Auto), the document states that performance was evaluated against "pre-defined acceptance criteria" but does not explicitly describe how the ground truth for those criteria was established, though it likely involved expert annotations or established clinical metrics.
8. The Sample Size for the Training Set
- The document states: "The data used to train these machine learning algorithms were sourced from multiple clinical sites from urban centers and from different countries." However, the specific sample size for the training set is not provided for any of the modules. It only mentions that the data was selected for good distribution of patient demographics, scanner, and image parameters.
9. How the Ground Truth for the Training Set Was Established
- The document does not explicitly describe how the ground truth for the training set was established. It only states that the training data "were sourced from multiple clinical sites from urban centers and from different countries." It also notes that "the separation into training versus validation datasets is made on the study level to ensure no overlap between the two sets." This suggests that the training data would have had associated ground truth data (e.g., expert annotations, clinical measurements) to enable supervised learning, but the method of establishing that ground truth is not detailed.
{0}------------------------------------------------
Image /page/0/Picture/0 description: The image shows the logo of the U.S. Food and Drug Administration (FDA). On the left is the seal of the Department of Health & Human Services. To the right of the seal is the FDA logo in blue, with the words "U.S. FOOD & DRUG" on one line and "ADMINISTRATION" on the line below. The logo is simple and professional, and it is easily recognizable.
Circle Cardiovascular Imaging Inc. Omar Naimi Regulatory Affairs Analyst Suite 1800, 707 8 Avenue SW Calgary, AB T2P 1H5 Canada
Re: K242781
October 15, 2024
Trade/Device Name: cvi42 Software Application Regulation Number: 21 CFR 892.2050 Regulation Name: Medical Image Management And Processing System Regulatory Class: Class II Product Code: QIH, LLZ Dated: September 13, 2024 Received: September 16, 2024
Dear Omar Naimi:
We have reviewed your section 510(k) premarket notification of intent to market the device referenced above and have determined the device is substantially equivalent (for the indications for use stated in the enclosure) to legally marketed predicate devices marketed in interstate commerce prior to May 28, 1976, the enactment date of the Medical Device Amendments, or to devices that have been reclassified in accordance with the provisions of the Federal Food, Drug, and Cosmetic Act (the Act) that do not require approval of a premarket approval application (PMA). You may, therefore, market the device, subject to the general controls provisions of the Act. Although this letter refers to your product as a device, please be aware that some cleared products may instead be combination products. The 510(k) Premarket Notification Database available at https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/pmn.cfm identifies combination product submissions. The general controls provisions of the Act include requirements for annual registration, listing of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration. Please note: CDRH does not evaluate information related to contract liability warranties. We remind you, however, that device labeling must be truthful and not misleading.
If your device is classified (see above) into either class II (Special Controls) or class III (PMA), it may be subject to additional controls. Existing major regulations affecting your device can be found in the Code of Federal Regulations, Title 21, Parts 800 to 898. In addition, FDA may publish further announcements concerning your device in the Federal Register.
Additional information about changes that may require a new premarket notification are provided in the FDA guidance documents entitled "Deciding When to Submit a 510(k) for a Change to an Existing Device"
{1}------------------------------------------------
(https://www.fda.gov/media/99812/download) and "Deciding When to Submit a 510(k) for a Software Change to an Existing Device" (https://www.fda.gov/media/99785/download).
Your device is also subject to, among other requirements, the Quality System (QS) regulation (21 CFR Part 820), which includes, but is not limited to, 21 CFR 820.30, Design controls; 21 CFR 820.90, Nonconforming product; and 21 CFR 820.100, Corrective and preventive action. Please note that regardless of whether a change requires premarket review, the QS regulation requires device manufacturers to review and approve changes to device design and production (21 CFR 820.30 and 21 CFR 820.70) and document changes and approvals in the device master record (21 CFR 820.181).
Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act or any Federal statutes and regulations administered by other Federal agencies. You must comply with all the Act's requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part 801); medical device reporting of medical device-related adverse events) (21 CFR Part 803) for devices or postmarketing safety reporting (21 CFR Part 4, Subpart B) for combination products (see https://www.fda.gov/combination-products/guidance-regulatory-information/postmarketing-safety-reportingcombination-products); good manufacturing practice requirements as set forth in the quality systems (OS) regulation (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR Part 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR Parts 1000-1050.
All medical devices, including Class I and unclassified devices and combination product device constituent parts are required to be in compliance with the final Unique Device Identification System rule ("UDI Rule"). The UDI Rule requires, among other things, that a device bear a unique device identifier (UDI) on its label and package (21 CFR 801.20(a)) unless an exception or alternative applies (21 CFR 801.20(b)) and that the dates on the device label be formatted in accordance with 21 CFR 801.18. The UDI Rule (21 CFR 830.300(a) and 830.320(b)) also requires that certain information be submitted to the Global Unique Device Identification Database (GUDID) (21 CFR Part 830 Subpart E). For additional information on these requirements, please see the UDI System webpage at https://www.fda.gov/medical-device-advicecomprehensive-regulatory-assistance/unique-device-identification-system.
Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to https://www.fda.gov/medical-device-safety/medical-device-reportingmdr-how-report-medical-device-problems.
For comprehensive regulatory information about medical devices and radiation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/medicaldevices/device-advice-comprehensive-regulatory-assistance) and CDRH Learn (https://www.fda.gov/training-and-continuing-education/cdrh-learn). Additionally, you may contact the Division of Industry and Consumer Education (DICE) to ask a question about a specific regulatory topic. See the DICE website (https://www.fda.gov/medical-device-advice-comprehensive-regulatory
{2}------------------------------------------------
assistance/contact-us-division-industry-and-consumer-education-dice) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).
Sincerely,
Jessica Lamb
Jessica Lamb, Ph.D. Assistant Director DHT8B: Division of Radiological Imaging Devices and Electronic Products OHT8: Office of Radiological Health Office of Product Evaluation and Quality Center for Devices and Radiological Health
Enclosure
{3}------------------------------------------------
Indications for Use
Submission Number (if known)
K242781
Device Name
cvi42 Software Application
Indications for Use (Describe)
cvi42 is intended to be used for viewing, post-processing, qualitative and quantitative evaluation of cardiovascular magnetic resonance (MR) images and computed tomography (CT) images in a Digital Imaging and Communications in Medicine (DICOM) Standard format.
lt enables:
· Importing cardiac MR & CT Images in DICOM format.
• Supporting clinical diagnostics by qualitative analysis of cardiac MR & CT images using display functionality such as panning, windowing, zooming, navigation through series/slices and phases, 3D reconstruction of images including multiplanar reconstructions of the images.
• Supporting clinical diagnostics by quantitative measurement of the heart and adjacent vessels in cardiac MR & CT images, specifically signal intensity, distance, area, volume, and mass.
• Supporting clinical diagnostics by using area and volume for measuring cardiac function and derived parameters cardiac output and cardiac index in long axis and short axis cardiac MR & CT images.
• Flow quantifications based on velocity encoded cardiac MR images (including two and four dimensional flow analysis).
• Strain analysis of cardiac MR images by providing measurements of 2D LV myocardial function (displacement, velocity, strain, strain rate, time to peak, and torsion).
· Supporting clinical diagnostics of cardiac CT images including quantitative measurements of calcified plaques in the coronary arteries (calcium scoring), specifically Agatston and volume and mass calcium scores, visualization and quantitative measurement of heart structures including coronaries, femoral, aortic, and mitral valves.
· Evaluating CT and MR images of blood vessels. Combining digital image processing and visualization tools such as multiplanar reconstruction (MPR), thin/thick maximum intensity projection (MIP), inverted MIP thin/thick, volume rendering technique (VRT), curved planar reformation (CPR), processing tools such as bone removal (based on both single energy and dual energy) table removal and evaluation tools (vessel centerline calculation, lumen calculation, stenosis calculation) and reporting tools (lesion location, lesion characteristics) and key images. The software package is designed to support the physician in confirming the presence of physician identified lesion in blood vessels and evaluation, documentation and follow up of any such lesions.
cvi42 shall be used by qualified medical professionals, experienced in examining and evaluating cardiovascular MR or CT images, for the purpose of obtaining diagnostic information as part of a comprehensive diagnostic decision-making process. cvi42 is a software application that can be used as a stand-alone product or in a networked environment.
The target population for cvi42 and its manual workflows is not restricted; however, cvi42's semiautomated machine learning algorithms, included in the MR Function and CORE CT modules, are intended for an adult population. Further, image acquisition by a cardiac MR or CT scanner may limit the use of the software for certain sectors of the general public.
{4}------------------------------------------------
cvi42 shall not be used to view or analyze images of any part of the body except the cardiac images acquired from a cardiovascular magnetic resonance or computed tomography scanner.
Type of Use (Select one or both, as applicable)
Prescription Use (Part 21 CFR 801 Subpart D)
Over-The-Counter Use (21 CFR 801 Subpart C)
CONTINUE ON A SEPARATE PAGE IF NEEDED.
This section applies only to requirements of the Paperwork Reduction Act of 1995.
DO NOT SEND YOUR COMPLETED FORM TO THE PRA STAFF EMAIL ADDRESS BELOW.
The burden time for this collection of information is estimated to average 79 hours per response, including the time to review instructions, search existing data sources, gather and maintain the data needed and complete and review the collection of information. Send comments regarding this burden estimate or any other aspect of this information collection, including suggestions for reducing this burden, to:
Department of Health and Human Services Food and Drug Administration Office of Chief Information Officer Paperwork Reduction Act (PRA) Staff PRAStaff@fda.hhs.gov
"An agency may not conduct or sponsor, and a person is not required to respond to, a collection of information unless it displays a currently valid OMB number."
{5}------------------------------------------------
Image /page/5/Picture/2 description: The image shows the logo for Circle Cardiovascular Imaging. The logo features a stylized green and yellow circle above the word "circle" in gray lowercase letters. Below "circle" are the words "CARDIOVASCULAR IMAGING" in smaller, gray, uppercase letters.
The following 510(k) summary of safety and effectiveness information is submitted in accordance with the requirements of the Safe Medical Device Act 1990 and 21 CFR 807.92(c).
l. SUBMITTER
| Submitter's Name: | Circle Cardiovascular Imaging, Inc. |
|---|---|
| Address: | Suite 1800 – 707 8th Ave SW, Calgary, AB, Canada, T2P 1H5 |
| Date Prepared: | October 11 2024 |
| Telephone Number: | +1 587-686-0784 |
| Contact Person : | Omar Naimi |
| Email: | omar.naimi@circlecvi.com |
ll. DEVICE
| 510(k): | K242781 |
|---|---|
| Name of the Device: | cvi42 Software Application |
| Short Brand Name: | cvi42 |
| Common or Usual Name: | Automated Radiological Image Processing Software |
| Classification Name: | Medical image management and processing system |
| Proposed Classification: | Device Class: II |
| Product Codes: QIH, LLZ | |
| Regulation Number: 21 CFR 892.2050 |
���. PREDICATE DEVICE
The primary predicate is cmr2 under K082628, and the additional predicates are ct42 under K111373, cvi42 vascular add-on under K141480, cvi42 Auto under K213998, Strain Module under 232661, and CT Function under 241038. Each of the predicate devices are manufactured by Circle Cardiovascular Imaging Inc.
The predicate devices have not been subject to a design-related recall.
{6}------------------------------------------------
IV. DEVICE DESCRIPTION
cvi42 Software Application ("cvi42") is a software as a medical device (SaMD) that is intended for evaluating CT and MR images of the cardiovascular system. Combining digital image processing, visualization, quantification, and reporting tools, cvi42 is designed to support physicians in the evaluation and analysis of cardiovascular imaqing studies.
cvi42 uses machine learning techniques to aid in semi-automatic contouring of regions of interest in cardiac MR or CT images.
The data used to train these machine learning algorithms were sourced from multiple clinical sites from urban centers and from different countries. When selecting data for training, the importance of model generalization was considered and data was selected such that a good distribution of patient demographics, scanner, and image parameters were represented. The separation into training versus validation datasets is made on the study level to ensure no overlap between the two sets. As such, different scans from the same study were not split between the training and validation datasets. None of the cases used for model validation were used for training the machine learning models.
cvi42 has a graphical user interface which allows users to analyze cardiac MR & CT images qualitatively and quantitatively.
cvi42 accepts uploaded data files previously acquired by MR or CT scanners or other data collection equipment but does not interface directly with such equipment. Its functionality is independent of the type of vender acquisition equipment. The analysis results are available onscreen and can be saved with the software for future review.
{7}------------------------------------------------
| Measurement [units] | Description | Application |
|---|---|---|
| Distance [mm] | Length between two points, for bothcurved lines (splines) and straight lines,including the diameter (including min,max, average) resulting from closedsplines and depth | Diameter & depth of cardiovascularstructures of interest |
| Perimeter [mm] | The perimeter of a contour (closed spline) | Perimeter of cardiovascular structures ofinterest |
| Area [cm²] | The area within contour(s) | Area of cardiovascular structures of interest |
| Signal intensity [HU](modality CT) / Intensity[unitless] (modality MR) | Modality CT: Hounsfield value (inHounsfield Units, HU) of the underlyingpixelsModality MR: Intensity / shade of grey(high, intermediate, low) of underlyingpixels | Intensity of pixels in cardiovascularstructures of interest |
| Volume [mm³ or mL] | The volume within contour(s) | Volume of cardiovascular structures ofinterest |
| Coordinates [mm, mm, mm] | Location in the x-, y-, and z-planes of apoint | Coordinates of points of interest on a 3Drendering, for export purposes |
| Mass [g] | The mass within contour(s) | Mass of cardiovascular structures of interest |
| Displacement [mm ordegree] | The displacement vector represents theposition of a point with respect to theposition of that point in the reference (enddiastole) phase. | Strain within cardiovascular structures ofinterest (e.g., myocardium) |
| Agatston Score [HU] | Industry-standard measure for coronarycalcium based on volume and intensity ofcalcified plaque | For assessing overall calcified plaqueburden in coronary arteries. |
| Angle [degrees] | The angle of an object/structure ofinterest | Angle between two lines of interest |
| Stenosis [%] | The narrowing of a vessel in area ordiameter compared to a normal referencelocation | For measuring an abnormal narrowing in anartery |
| Velocity [mL/min or cm/s] | The velocity of moving objects withincontour(s) | Velocity within cardiovascular structures ofinterest (e.g., blood flow) |
| Strain [%] | Strain is a measure of the deformation inshape and dimension of the heart muscleduring the cardiac cycle. | Strain within cardiovascular structures ofinterest (e.g., myocardium) |
| Strain Rate [1/s] | Derivative of strain with respect to time | Strain within cardiovascular structures ofinterest, as above |
| Time to Peak [ms] | Trigger time elapsed from the first phasetill the phase where the peak strain hasbeen reached. | Strain within cardiovascular structures ofinterest, as above |
| Torsion [degree/cm] | The difference in rotation between theapical and basal slices divided by theapical and basal slices. Notecircumferential displacement representsan angle. | Strain within cardiovascular structures ofinterest, as above |
| End Diastolic Volume [mL] | LV/RV cavity volume at the phasedefined as the ED | Calculated clinical data for LV/RV |
| End Systolic Volume [mL] | LV/RV cavity volume at the phasedefined as the ES | Calculated clinical data for LV/RV |
| Stroke Volume [mL] | Stroke volume is the volume of bloodpumped out of the LV/RV during eachcardiac contraction and is represented bythe difference of EDV and ESV. | Calculated clinical data for LV/RV |
| Ejection Fraction [%] | Ejection fraction is measured as apercentage of the total amount of blood inLV/RV that is pumped out with eachcardiac cycle. It is calculated by dividingthe SV by EDV. | Calculated clinical data for LV/RV |
| Cardiac Output [L/min] | Cardiac output is the amount of bloodpumped by the heart in a minute and iscalculated by multiplying the SV withheart rate per minute. | Calculated clinical data for LV/RV |
| Cardiac Index [L/min/m²] | Cardiac index is a hemodynamicparameter that relates the CO from LV inone minute to BSA and is obtained bydividing the CO by BSA. | Calculated clinical data for LV |
| End Diastolic Mass [g] | LV myocardial mass at the phase definedas the ED and is calculated by multiplyingthe myocardial volume in ED phase withmyocardial density (1.05 g/ml). | Calculated clinical data for LV |
| End Systolic Mass [g] | LV myocardial mass at the phase definedas the ES and is calculated by multiplyingthe myocardial volume in ES phase withmyocardial density (1.05 g/ml). | Calculated clinical data for LV |
| Body Surface Area [m²] | The total surface area of the body | Surface area of the patient body used inmedical indicators or assessments |
{8}------------------------------------------------
{9}------------------------------------------------
V. INTENDED USE / INDICATIONS FOR USE
Intended Use
cvi42 is intended to be used by qualified medical professionals for viewing, post-processing and quantitative evaluation of cardiovascular magnetic resonance (MR) images and cardiovascular computed tomography (CT) images in a Digital Imaging and Communications in Medicine Standard format, for the purpose of obtaining diagnostic information as part of a comprehensive diaqnostic decision-making process
Indications for Use
cvi42 is intended to be used for viewing, post-processing, qualitative evaluation of cardiovascular magnetic resonance (MR) images and computed tomography (CT) images in a Digital Imaging and Communications in Medicine (DICOM) Standard format.
lt enables:
- . Importing cardiac MR & CT Images in DICOM format.
- . Supporting clinical diagnostics by qualitative analysis of cardiac MR & CT images using display functionality such as panning, windowing, zooming, navigation through series/slices and phases, 3D reconstruction of images including multiplanar reconstructions of the images.
- . Supporting clinical diagnostics by quantitative measurement of the heart and adjacent vessels in cardiac MR & CT images, specifically signal intensity, distance, area, volume, and mass.
- . Supporting clinical diagnostics by using area and volume for measuring cardiac function and derived parameters cardiac output and cardiac index in long axis and short axis cardiac MR & CT images.
- . Flow quantifications based on velocity encoded cardiac MR images (including two and four dimensional flow analysis).
- . Strain analysis of cardiac MR images by providing measurements of 2D LV myocardial function (displacement, velocity, strain, strain rate, time to peak, and torsion).
- . Supporting clinical diagnostics of cardiac CT images including quantitative measurements of calcified plaques in the coronary arteries (calcium scoring), specifically Agatston and volume and mass calcium scores, visualization and quantitative measurement of heart structures including coronaries, femoral, aortic, and mitral valves.
- . Evaluating CT and MR images of blood vessels. Combining digital image processing and visualization tools such as multiplanar reconstruction (MPR), thin/thick maximum intensity projection (MIP), inverted MIP thin/thick, volume rendering technique (VRT), curved planar reformation (CPR), processing tools such as bone removal (based on both single energy and dual energy) table removal and evaluation tools (vessel centerline calculation, lumen calculation, stenosis calculation) and reporting tools (lesion location, lesion characteristics) and key images. The software package is designed to support the
{10}------------------------------------------------
physician in confirming the presence or absence of physician identified lesion in blood vessels and evaluation, documentation and follow up of any such lesions.
cvi42 shall be used by qualified medical professionals, experienced in examining and evaluating cardiovascular MR or CT images, for the purpose of obtaining diagnostic information as part of a comprehensive diagnostic decision-making process. cvi42 is a software application that can be used as a stand-alone product or in a networked environment.
The target population for cvi42 and its manual workflows is not restricted; however, cvi42's semiautomated machine learning algorithms, included in the MR Function and CORE CT modules, are intended for an adult population. Further, image acquisition by a cardiac MR or CT scanner may limit the use of the software for certain sectors of the general public.
cvi42 shall not be used to view or analyze images of any part of the body except the cardiac images acquired from a cardiovascular magnetic resonance or computed tomography scanner.
VI. COMPARISON WITH PREDICATE DEVICE
The detailed analysis of the subject device and the predicate device (shown in Table 2 and Table 3) demonstrates that the subject device is substantially equivalent in indications for use / intended use, technological characteristics, functionality, and operating principles with the predicates (K092628, K111373, K141480, K213998, K232661, and K241038). Of the three characteristics (technical, biological, and clinical) required for the demonstration of equivalence, biological characteristics are not applicable since both the subject device and predicate device are software as a medical device application with no tangible component interfacing with the body.
{11}------------------------------------------------
| Table 2. Subject Device Intended Use / Indications for Use | |
|---|---|
| ------------------------------------------------------------ | -- |
| Subject Device | Primary Predicatecmr42 (K082628) | Predicatect42 (K111373) | Predicatecvi42 (K141480) | Predicatecvi42 Auto (K213998) | PredicateStrain (K232661) | PredicateCT Function (K241038) | ||
|---|---|---|---|---|---|---|---|---|
| cvi42 Software Application (K242781) | Manufactured by Circle | Manufactured by Circle | Manufactured by Circle | Manufactured by Circle | Manufactured by Circle | Manufactured by Circle | ||
| Manufactured by Circle | Intended Use | Viewing, post-processing,qualitative and quantitativeevaluation of cardiovascular MRimages in DICOM format. | Viewing, post-processing, qualitativeand quantitative evaluation ofcardiovascular CT images in DICOMformat. | Viewing, post-processing, qualitativeand quantitative evaluation of bloodvessels and cardiovascular MR andCT images in DICOM format. | Viewing, post-processing, qualitativeand quantitative evaluation of bloodvessels and cardiovascular MR andCT images in DICOM format. | The Myocardial Strain SoftwareApplication is intended for qualitativeand quantitative evaluation ofcardiovascular MR images in aDICOM Standard format. Asperquisite, the user confirmsendocardial and epicardial contours ina reference phase, and the softwaretracks features over the cardiac cycleand computed 2D myocardialdeformation and movement (e.g.,strain, displacement, velocity). | The Cardiac CT Function SoftwareApplication is intended for qualitativeand quantitative evaluation ofcardiovascular CT images in a DICOMStandard format, to calculate anddisplay cardiac function metrics (e.g.,end diastolic volume, end systolicvolume, stroke volume, ejection fractioncardiac output, cardiac index, and LVmyocardial mass). | |
| Intended Use | cvi42 is intended to be used by qualified medical professionals for viewing, post-processing and quantitative evaluation of cardiovascular magnetic resonance (MR) images and cardiovascular computed tomography (CT) images in a Digital Imagingand Communications in Medicine Standard format, for the purpose of obtaining diagnostic information as part of a comprehensive diagnostic decision-making process | Indications for Use | cmr42 is intended to be used forviewing, post-processing andquantitative evaluation ofcardiovascular magnetic resonance(MR) images in a Digital Imagingand Communications in Medicine(DICOM) Standard format.It enables;• Importing Cardiac MR Images inDICOM format• Supporting clinical diagnostics byqualitative analysis of the cardiacMR images using displayfunctionality such as panning,windowing, zooming, navigationthrough series/slices and phases.• Supporting clinical diagnostics byquantitative measurement of theheart and adjacent vessels incardiac MR images, specificallydistance, area, volume and mass• Supporting clinical diagnostics byusing area and volumemeasurements for measuring LVfunction and derived parameterscardiac output and cardiac index inlong axis and short axis cardiac MRimages.• Flow quantifications based onvelocity encodes images | ct42 is intended to be used for viewing,post-processing and quantitativeevaluation of cardiovascular computedtomography (CT) images in a DigitalImaging and Communications inMedicine (DICOM) Standard format.It enables:• Importing Cardiac CT Images inDICOM format• Supporting clinical diagnostics byqualitative analysis of the cardiac CTimages using display functionalitysuch as panning, windowing,zooming, navigation throughseries/slices and phases, 3Dreconstruction of images includingmulti-lanner reconstructions of theimages.• Supporting clinical diagnostics byquantitative measurement of the heartand adjacent vessels in cardiac CTimages, specifically distance, area,volume and mass• Supporting clinical diagnostics byusing area and volume measurementsfor measuring LV function and derivedparameters cardiac output and cardiacindex in long axis and short axiscardiac CT images. | cvi42 vascular analysis add-on is animage analysis software package add-on for evaluating CT and MR imagesof blood vessels. Combining digitalimage processing and visualizationtools such as multiplanarreconstruction (MPR), thin/thinkmaximum intensity projection (MIP)thin and think, inverted MIP thin andthink, volume rendering technique(VRT), curved planner reformation,processing tools such as boneremoval (based on both single energyand dual energy) table removal andevaluation tools (vessel centerlinecalculation, lumen calculation,stenosis calculation) and reportingtools (lesion location, lesioncharacteristics) and key images), thesoftware package is designed tosupport the physician in conformingthe presence or absence of physicianidentified lesion in blood vessels andevaluation, documentation and followup of any such lesions.It shall be used by qualified medicalprofessionals, experienced inexamining and evaluatingcardiovascular CT or MR images, forthe purpose of obtaining diagnostic | cvi42 Auto is intended to be used forviewing, post-processing, qualitativeand quantitative evaluation ofcardiovascular magnetic resonance(MR) and computed tomography (CT)images in a Digital Imaging andCommunications in Medicine (DICOM)Standard format.It enables a set of tools to assistphysicians in qualitative assessmentof cardiac images and quantitativemeasurements of the heart andadjacent vessels; perform calciumscoring; and to confirm the presenceor absence of physician-identifiedlesion in blood vessels.The target population for cvi42 Auto'smanual workflows is not restricted;however, cvi42 Auto's semi-automated machine learningalgorithms are intended for an adultpopulation.cvi42 Auto shall be used only forcardiac images acquired from an MRor CT scanner. It shall be used byqualified medical professionals,experienced in examining andevaluating cardiovascular MR or CT | The Myocardial Strain SoftwareApplication is intended for qualitativeand quantitative evaluation ofcardiovascular magnetic resonance(CMR) images. It providesmeasurements of 2D LV myocardialfunction (displacement, velocity,strain, strain rate, time to peak, andtorsion); these measurements areused by qualified medicalprofessionals, experiences inexamining and evaluating CMRimages, for the purpose of obtainingdiagnostic information for patients withsuspected heart disease as part of acomprehensive diagnostic decision-making process. | The Cardiac CT Function SoftwareApplication is indicated to be use withmulti-phase, multi-slice cardiovascularCT angiography images to assistqualified medical professionals inassessing and evaluating cardiacfunction. CT Function includes manualand semi-automatic heart segmentationof 2 chambers (LV and RV) andcalculation of cardiac function metricsincluding end diastolic volume, endsystolic volume, stroke volume, ejectionfraction, cardiac output, cardiac index,and LV myocardial mass. |
| Indications for Use | cvi42 is intended to be used for viewing, post-processing, qualitative and quantitative evaluation of cardiovascular magnetic resonance (MR) images and computed tomography (CT) images in a Digital Imaging and Communications in Medicine(DICOM) Standard format. | |||||||
| It enables:Importing cardiac MR & CT Images in DICOM format. Supporting clinical diagnostics by qualitative analysis of cardiac MR & CT images using display functionality such as panning, windowing, zooming, navigation through series/slices and phases, 3D reconstruction of images including multiplanar reconstructions of the images. Supporting clinical diagnostics by quantitative measurement of the heart and adjacent vessels in cardiac MR & CT images, specifically signal intensity, distance, area, volume, and mass. Supporting clinical diagnostics by using area and volume for measuring cardiac function and derived parameters cardiac output and cardiac index in long axis and short axis cardiac MR & CT images. Flow quantifications based on velocity encoded cardiac MR images (including two and four dimensional flow analysis). Strain analysis of cardiac MR images by providing measurements of 2D LV myocardial function (displacement, velocity, strain, strain rate, time to peak, and torsion). Supporting clinical diagnostics of cardiac CT images including quantitative measurements of calcified plaques in the coronary arteries (calcium scoring), specifically Agatston and volume and mass calcium scores, visualization and quantitative measurement of heart structures including coronaries, femoral, aortic, and mitral valves. Evaluating CT and MR images of blood vessels. Combining digital image processing and visualization tools such as multiplanar reconstruction (MPR), thin/thick maximum intensity projection (MIP), inverted MIP thin/thick, volume rendering technique (VRT), curved planar reformation (CPR), processing tools such as bone removal (based on both single energy and dual energy) table removal and evaluation tools (vessel centerline calculation, lumen calculation, stenosis calculation) and reporting tools (lesion location, lesion characteristics) and key images. The software package is designed to support the physician in confirming the presence or absence of physician identified lesion in blood vessels and evaluation, documentation and follow up of any such lesions. cvi42 shall be used by qualified medical professionals, experienced in examining and evaluating cardiovascular MR or CT images, for the purpose of obtaining diagnostic information as part of a comprehensive diagnostic decision-making process.cvi42 is a software application that can be used as a stand-alone product or in a networked environment.The target population for cvi42 and its manual workflows is not restricted; however, cvi42's semi-automated machine learning algorithms, included in the MR Function and CORE CT modules, are intended for an adult population. Further, image acquisition by a cardiac MR or CT scanner may limit the use of the software for certain sectors of the general public.cvi42 shall not be used to view or analyze images of any part of the body except the cardiac images acquired from a cardiovascular magnetic resonance or computed tomography scanner. |
{12}------------------------------------------------
Table 3. Predicate Device Intended Use / Indications for Use
Circle Cardiovascular Imaging Inc.
{13}------------------------------------------------
| Primary Predicate | Predicate | Predicate | Predicate | Predicate | Predicate |
|---|---|---|---|---|---|
| cmr42 (K082628) | ct42 (K111373) | cvi42 (K141480) | cvi42 Auto (K213998) | Strain (K232661) | CT Function (K241038) |
| Manufactured by Circle | Manufactured by Circle | Manufactured by Circle | Manufactured by Circle | Manufactured by Circle | Manufactured by Circle |
| It shall be used by qualified medicalprofessionals, experienced inexamining and evaluatingcardiovascular MR images, for thepurpose of obtaining diagnosticinformation as part of acomprehensive diagnostic decision-making process. cmr42 is a softwareapplication that can be used as astand-alone product or in anetworked environment.The target population for the cmr42is not restricted, however the imageacquisition by a cardiac magneticresonance scanner may limit theuse of the device for certain sectorsof the general public.cmr42 shall not be used to view oranalyze images of any part of thebody except the cardiac magneticresonance images acquired from acardiovascular magnetic resonancescanner. | • Supporting clinical diagnostics byquantitative measurements of calcifiedplaques in the coronary arteries(calcium scoring), specificallyAgatston and volume and masscalcium scoresIt shall be used by qualified medicalprofessionals, experienced inexamining and evaluatingcardiovascular CT images, for thepurpose of obtaining diagnosticinformation as part of acomprehensive diagnostic decision-making process. ct42 is a softwareapplication that can be used as astand-alone product or in a networkedenvironment.The target population for the ct42 is notrestricted, however the imageacquisition by a cardiac CT scannermay limit the use of the device forcertain sectors of the general public.ct42 shall not be used to view oranalyze images of any part of thebody except the cardiac CT imagesacquired from a cardiovascular CTscanner. | information as part of acomprehensive diagnostic decision-making process. cvi42 is a softwareapplication that can be used as astand-alone product or in a networkedenvironment.The target population for the cvi42 isnot restricted. | images, for the purpose of obtainingdiagnostic information as part of acomprehensive diagnostic decision-making process. |
{14}------------------------------------------------
| Table 3. Regulatory and technological features comparison. | |||||||
|---|---|---|---|---|---|---|---|
| Feature | Subject Devicecvi42 Software Application(K242781)Manufactured by Circle | Primary Predicatecmr42 (K082628)Manufactured by Circle | Predicatect42 (K111373)Manufactured by Circle | Predicatecvi42 (K141480)Manufactured by Circle | Predicatecvi42 Auto (K213998)Manufactured by Circle | PredicateStrain (K232661)Manufactured by Circle | PredicateCT Function (K241038)Manufactured by Circle |
| Device Class | II | II | II | II | II | II | II |
| Device Classification | QIH, LLZ | LLZ | LLZ | LLZ | QIH, LLZ | LLZ | QIH, LLZ |
| Regulation Name | Medical image managementand processing system | Picture Archiving andCommunications System | Picture Archiving andCommunications System | Picture Archiving andCommunications System | Medical image managementand processing system | Medical image managementand processing system | Medical image managementand processing system |
| Regulation Number | 21 CFR 892.2050 | 21 CFR 892.2050 | 21 CFR 892.2050 | 21 CFR 892.2050 | 21 CFR 892.2050 | 21 CFR 892.2050 | 21 CFR 892.2050 |
| Imaging Modalities | MR and CT | MR | CT | MR and CT | MR and CT | MR | CT |
| DICOM Compliant | Yes | Yes | Yes | Yes | Yes | Yes | Yes |
| Import and display MR/CTimages | Yes | Yes (MR only) | Yes (CT only) | Yes | Yes | Yes (MR only) | Yes (CT only) |
| Post process CMR/CCT images | Yes | Yes (MR only) | Yes (CT only) | Yes | Yes | Yes (MR only) | Yes (CT only) |
| Images can be displayed bystudy and series | Yes | Yes | N/A | N/A | N/A | N/A | N/A |
| Store images | Yes | Yes | N/A | N/A | N/A | N/A | N/A |
| 2D Imaging | Yes | Yes | N/A | N/A | N/A | N/A | N/A |
| 3D Imaging | Yes | No | Yes | Yes | Yes | Yes | Yes |
| Multiplanar Reformat (MPR) | Yes | No | Yes | Yes | Yes | No | Yes |
| Navigation Tools | Panning,Windowing,Zooming,Series/slices and phases | Panning,Windowing,ZoomingSeries/slices and phases | N/A | N/A | N/A | N/A | N/A |
| Measurements | DistancePerimeterAreaSignal IntensityVolumeCoordinatesMassDisplacementAgatston ScoreAngleStenosisVelocityStrainStrain RateTime to PeakTorsionEnd Diastolic Volume (EDV)End Systolic Volume (ESV)Stroke Volume (SV)Ejection Fraction (EF)Cardiac Output (CO) | DistancePerimeterAreaSignal IntensityVolumeMassCoordinates | DistancePerimeterAreaSignal IntensityVolumeCoordinatesAgatston Score | DistancePerimeterAreaSignal IntensityVolumeCoordinatesAngleStenosis | DistancePerimeterAreaSignal IntensityVolumeAgatston ScoreStenosisEnd Diastolic Volume (EDV)End Systolic Volume (ESV)Stroke Volume (SV)Ejection Fraction (EF)Cardiac Output (CO)End Diastolic Mass (EDV)End Systolic Mass (ESV)Body Surface Area (BSA) | DisplacementVelocityStrainStrain RateTime to PeakTorsion | End Diastolic Volume (EDV)End Systolic Volume (ESV)Stroke Volume (SV)Ejection Fraction (EF)Cardiac Output (CO)Cardiac Index (CI)End Diastolic Mass (EDM)End Systolic Mass (ESM)Body Surface Area (BSA) |
| Feature | Subject Devicecvi42 Software Application(K242781)Manufactured by Circle | Primary Predicatecmr42 (K082628)Manufactured by Circle | Predicatect42 (K111373)Manufactured by Circle | Predicatecvi42 (K141480)Manufactured by Circle | Predicatecvi42 Auto (K213998)Manufactured by Circle | PredicateStrain (K232661)Manufactured by Circle | PredicateCT Function (K241038)Manufactured by Circle |
| Cardiac Index (CI)End Diastolic Mass (EDM)End Systolic Mass (ESM)Body Surface Area (BSA) | |||||||
| Quantitative assessment ofcardiac function | Manual segmentation, andsemi-automatic segmentationusing Machine Learningtechnique of four heartchambers in long and short-axis views | Manual segmentation of fourheart chambers in long andshort-axis views | Manual segmentation, andsemi-automatic segmentationof four heart chambers in short-axis views | Manual segmentation, andsemi-automatic segmentationof four heart chambers in longand short-axis views | Manual segmentation, andsemi-automatic segmentationusing Machine Learningtechnique of four heartchambers in long and short-axis views | Manual segmentation, 2Dfunctional analysis ofmyocardial deformation | Semi-automatic determinationof epicardial and endocardialcontours, via segmentation ofthe LV cavity, LV myocardium,and RV cavity and the ED andES phases using MachineLearning Techniques |
| Assessment of cardiac blood flow | Quantification of blood flowusing MR velocity encodedimages. | Quantification of blood flowusing MR velocity encodedimages. | N/A | N/A | N/A | N/A | N/A |
| Centerline placement in coronaryvessels | Manual and semi-automaticusing Machine Learningtechnique | Manual | Manual and semi-automatic | Manual and semi-automatic | Manual and semi-automaticusing Machine Learningtechnique | No | No |
| Calcium Scoring | Yes, using ML methodology | No | Yes, using non-MLmethodology | No | Yes, using ML methodology | No | No |
| Workstation operating system | macOS,Microsoft Windows | macOS,Microsoft Windows | macOS,Microsoft Windows | macOS,Microsoft Windows | macOS,Microsoft Windows | macOS,Microsoft Windows | macOS,Microsoft Windows |
Circle Cardiovascular Imaging Inc.
Non-Confidential
{15}------------------------------------------------
NOTE: Some items have been marked Not Applicatity is covered via other predicate devices in which the subject device is being ompared to.
{16}------------------------------------------------
PERFORMANCE DATA AND TESTING VII.
Performance testing was conducted to verify compliance with specified design requirements in accordance with ISO 13485:2016, BS EN 62304:2006, ISO 14971:2019, and DICOM standards.
Verification and validation testing were conducted to ensure specifications and performance of the device and were performed per the FDA Guidance "Technical Performance Assessment of Quantitative Imaging in Radiological Device Premarket Submission". No clinical studies were necessary to support substantial equivalence.
cvi42 has been tested according to the specifications that are documented in a Master Software Test Plan. Testing is an integral part of Circle Cardiovascular Imaging Inc.'s software development as described in the company's product development process.
Validation of non-Machine Learning Outputs
The validation of non-ML or rule-based algorithms and mathematical outputs in cvi42 is performed through general in-house software QA verification and validation process including unit tests, content/phantom tests, quantitative and qualitative analysis, and visual/manual evaluation. Some more complex algorithms, such as Strain measurement, however, have undergone additional validation to ensure the safe and effective use of the software.
Strain: 2D LV
The tracking performance and the clinically relevant Global Longitudinal and Global Circumferential strains were validated using a complimentary combination of simple and realistic phantoms, real MRI data, and analytical solutions. The tracking performance was evaluated with simple analytical phantoms generated with variable input parameters; the deformation field generated by the strain module was evaluated on realistic phantoms with artificially imposed known deformation field and perturbations; and the performance of the constrained tissue tracking algorithm was also compared to manual tracking in ES phase by three expert readers. The computation of the deformation metrics from the tracked deformations were evaluated analytically.
{17}------------------------------------------------
Validation of Machine Learning Derived Outputs
The machine learning algorithms of cvi42 have been trained and tested on images acquired from major vendors of MR and CT imaging devices. All data used for validation were not used during the development of the training algorithms. In general, image information for samples is anonymized and limited to ePHI-free DICOM headers and at least 50% of the data came from a U.S. population. All performance testing results have met Circle's pre-defined acceptance criteria.
cvi42 Auto: MR Function & CORE CT
The machine learning algorithms of cvi42 Auto (MR-CMR Function, CORE CT Coronary, and CORE CT-Calcium) have been trained and tested on images acquired from major vendors of MR and CT imaging devices. All data used for validation were not used during the development of the training algorithms.
Across all MR and CT machine manufacturers, n = 235 anonymized patient images were used for the validation of cvi42 Auto. This translates into 70 samples for Coronary Analysis, 102 samples for Calcium analysis, 63 samples for SAX Function contouring, 63 for each of 2-CV, 3-CV, and 4CV LAX function contouring, and 252 samples for Function Classification. Image information for all samples was anonymized and limited to ePHI-free DICOM headers. At least 50% of the data came from a U.S. population.
All performance testing results met Circle's pre-defined acceptance criteria.
- For CMR function analysis, the performance acceptance criteria were pre-defined to . evaluate the performance of the ML model based on classification accuracy defined by true positives (TP), true negatives (TN), false positives (FP), and false negatives (FN). Mean volume prediction error (Mean Absolute Error, or MAE) was also calculated. Series classification performance results were between 97 % - 100%. Volumetric MAE for SAX were between 7% - 10%, and volumetric MAE for LAX were between 5% - 9%.
- For Calcium analysis, the performance acceptance criteria were pre-defined to evaluate . the performance of the ML model based on classification accuracy defined by TP. TN. FP. and FN. Classification performance results were between 86% - 99%.
- For Coronary analysis, the performance acceptance criteria were pre-defined to evaluate . the centerline quality and performance (based on TP and FN), and success rate for relevant masks. Centerline performance results were between 82% - 94%. Mask performance results were between 98% - 100%.
CORE CT: CT Function
The Machine Learning (ML) algorithms of the CT Function Module have been trained and tested on images acquired from major vendors of CT imaging devices. All data used for validation were not used during the development of the ML algorithms. Image information for all samples was anonymized and limited to ePHI-free DICOM headers. The validation data was sourced from 9 different sites, with 90% of the data sampled from US sources. All performance testing results met Circle's pre-defined acceptance criteria.
For cardiac CT function analysis, the acceptance criteria were pre-defined to evaluate the
{18}------------------------------------------------
performance of the ML-based segmentation of Left Ventricle (LV) cavity, LV myocardium, and Right Ventricle (RV) cavity. The mean volume prediction error (Mean Absolute Error in predicted volumetric measures, or MAE), 3D Hausdorff Distance (HD), and Dice coefficient were used to evaluate the performance of the segmentation. Overall, comparable performance was achieved on all variability factors including scanner vendors, scanner tube current, pixel resolution, slice thickness, age group, and gender.
Compared to a reference standard established from three expert readers, the ML-based model is capable of segmenting the LV cavity with less than 10% difference in MAE. a Dice coefficient above 86%, a HD below 9.5 mm. and an EF bias of 1.3% with a 95% confidence interval of I-12. 14]. Similarly, the RV cavity is segmented with less than 18% MAE, a Dice coefficient above 85%, a HD below 18 mm, and an EF bias of -5.5% with a 95% confidence interval of [-15, 4.4]. Lastly, the LV myocardium is segmented with less than 17% MAE, a Dice coefficient above 82%, and a HD below 15 mm.
VIII. CONCLUSION
The information submitted in this premarket notification, including the performance testing and predicate device comparison, support the safety and effectiveness of cvi42 as compared to the predicate devices when used for the defined intended use.
§ 892.2050 Medical image management and processing system.
(a)
Identification. A medical image management and processing system is a device that provides one or more capabilities relating to the review and digital processing of medical images for the purposes of interpretation by a trained practitioner of disease detection, diagnosis, or patient management. The software components may provide advanced or complex image processing functions for image manipulation, enhancement, or quantification that are intended for use in the interpretation and analysis of medical images. Advanced image manipulation functions may include image segmentation, multimodality image registration, or 3D visualization. Complex quantitative functions may include semi-automated measurements or time-series measurements.(b)
Classification. Class II (special controls; voluntary standards—Digital Imaging and Communications in Medicine (DICOM) Std., Joint Photographic Experts Group (JPEG) Std., Society of Motion Picture and Television Engineers (SMPTE) Test Pattern).